Merge branch 'qed-introduce-devlink-health-support'

Igor Russkikh says:

====================
qed: introduce devlink health support

This is a followup implementation after series

https://patchwork.ozlabs.org/project/netdev/cover/20200514095727.1361-1-irusskikh@marvell.com/

This is an implementation of devlink health infrastructure.

With this we are now able to report HW errors to devlink, and it'll take
its own actions depending on user configuration to capture and store the
dump at the bad moment, and to request the driver to recover the device.

So far we do not differentiate global device failures or specific PCI
function failures. This means that some errors specific to one physical
function will affect an entire device. This is not yet fully designed
and verified, will followup in future.

Solution was verified with artificial HW errors generated, existing
tools for dump analysis could be used.

v7: comments from Jesse and Jakub
 - p2: extra edev check
 - p9: removed extra indents
v6: patch 4: changing serial to board.serial and fw to fw.app
v5: improved patch 4 description
v4:
 - commit message and other fixes after Jiri's comments
 - removed one patch (will send to net)
v3: fix uninit var usage in patch 11
v2: fix #include issue from kbuild test robot.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/qlogic/Kconfig

@@ -80,7 +80,7 @@ config QED
 	select CRC8
 	select NET_DEVLINK
 	help
-	  This enables the support for ...
+	  This enables the support for Marvell FastLinQ adapters family.
 
 config QED_LL2
 	bool
@@ -100,7 +100,8 @@ config QEDE
 	depends on QED
 	imply PTP_1588_CLOCK
 	help
-	  This enables the support for ...
+	  This enables the support for Marvell FastLinQ adapters family,
+	  ethernet driver.
 
 config QED_RDMA
 	bool

drivers/net/ethernet/qlogic/qed/Makefile

@@ -9,6 +9,7 @@ qed-y :=			\
 	qed_dcbx.o		\
 	qed_debug.o		\
 	qed_dev.o		\
+	qed_devlink.o		\
 	qed_hw.o		\
 	qed_init_fw_funcs.o	\
 	qed_init_ops.o		\

drivers/net/ethernet/qlogic/qed/qed.h

@@ -807,6 +807,7 @@ struct qed_dev {
 	struct qed_llh_info *p_llh_info;
 
 	/* Linux specific here */
+	struct qed_dev_info		common_dev_info;
 	struct  qede_dev		*edev;
 	struct  pci_dev			*pdev;
 	u32 flags;
@@ -849,7 +850,6 @@ struct qed_dev {
 	u32 rdma_max_srq_sge;
 	u16 tunn_feature_mask;
 
-	struct devlink			*dl;
 	bool				iwarp_cmt;
 };
 
@@ -981,6 +981,7 @@ void qed_bw_update(struct qed_hwfn *hwfn, struct qed_ptt *ptt);
 u32 qed_unzip_data(struct qed_hwfn *p_hwfn,
 		   u32 input_len, u8 *input_buf,
 		   u32 max_size, u8 *unzip_buf);
+int qed_recovery_process(struct qed_dev *cdev);
 void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn);
 void qed_hw_error_occurred(struct qed_hwfn *p_hwfn,
 			   enum qed_hw_err_type err_type);

drivers/net/ethernet/qlogic/qed/qed_dev.c

@@ -3973,6 +3973,7 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	struct qed_mcp_link_speed_params *ext_speed;
 	struct qed_mcp_link_capabilities *p_caps;
 	struct qed_mcp_link_params *link;
+	int i;
 
 	/* Read global nvm_cfg address */
 	nvm_cfg_addr = qed_rd(p_hwfn, p_ptt, MISC_REG_GEN_PURP_CR0);
@@ -4290,6 +4291,14 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		__set_bit(QED_DEV_CAP_ROCE,
 			  &p_hwfn->hw_info.device_capabilities);
 
+	/* Read device serial number information from shmem */
+	addr = MCP_REG_SCRATCH + nvm_cfg1_offset +
+		offsetof(struct nvm_cfg1, glob) +
+		offsetof(struct nvm_cfg1_glob, serial_number);
+
+	for (i = 0; i < 4; i++)
+		p_hwfn->hw_info.part_num[i] = qed_rd(p_hwfn, p_ptt, addr + i * 4);
+
 	return qed_mcp_fill_shmem_func_info(p_hwfn, p_ptt);
 }
 

drivers/net/ethernet/qlogic/qed/qed_devlink.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Marvell/Qlogic FastLinQ NIC driver
+ *
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+
+#include <linux/kernel.h>
+#include <linux/qed/qed_if.h>
+#include <linux/vmalloc.h>
+#include "qed.h"
+#include "qed_devlink.h"
+
+enum qed_devlink_param_id {
+	QED_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	QED_DEVLINK_PARAM_ID_IWARP_CMT,
+};
+
+struct qed_fw_fatal_ctx {
+	enum qed_hw_err_type err_type;
+};
+
+int qed_report_fatal_error(struct devlink *devlink, enum qed_hw_err_type err_type)
+{
+	struct qed_devlink *qdl = devlink_priv(devlink);
+	struct qed_fw_fatal_ctx fw_fatal_ctx = {
+		.err_type = err_type,
+	};
+
+	if (qdl->fw_reporter)
+		devlink_health_report(qdl->fw_reporter,
+				      "Fatal error occurred", &fw_fatal_ctx);
+
+	return 0;
+}
+
+static int
+qed_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter,
+			   struct devlink_fmsg *fmsg, void *priv_ctx,
+			   struct netlink_ext_ack *extack)
+{
+	struct qed_devlink *qdl = devlink_health_reporter_priv(reporter);
+	struct qed_fw_fatal_ctx *fw_fatal_ctx = priv_ctx;
+	struct qed_dev *cdev = qdl->cdev;
+	u32 dbg_data_buf_size;
+	u8 *p_dbg_data_buf;
+	int err;
+
+	/* Having context means that was a dump request after fatal,
+	 * so we enable extra debugging while gathering the dump,
+	 * just in case
+	 */
+	cdev->print_dbg_data = fw_fatal_ctx ? true : false;
+
+	dbg_data_buf_size = qed_dbg_all_data_size(cdev);
+	p_dbg_data_buf = vzalloc(dbg_data_buf_size);
+	if (!p_dbg_data_buf) {
+		DP_NOTICE(cdev,
+			  "Failed to allocate memory for a debug data buffer\n");
+		return -ENOMEM;
+	}
+
+	err = qed_dbg_all_data(cdev, p_dbg_data_buf);
+	if (err) {
+		DP_NOTICE(cdev, "Failed to obtain debug data\n");
+		vfree(p_dbg_data_buf);
+		return err;
+	}
+
+	err = devlink_fmsg_binary_pair_put(fmsg, "dump_data",
+					   p_dbg_data_buf, dbg_data_buf_size);
+
+	vfree(p_dbg_data_buf);
+
+	return err;
+}
+
+static int
+qed_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter,
+			      void *priv_ctx,
+			      struct netlink_ext_ack *extack)
+{
+	struct qed_devlink *qdl = devlink_health_reporter_priv(reporter);
+	struct qed_dev *cdev = qdl->cdev;
+
+	qed_recovery_process(cdev);
+
+	return 0;
+}
+
+static const struct devlink_health_reporter_ops qed_fw_fatal_reporter_ops = {
+		.name = "fw_fatal",
+		.recover = qed_fw_fatal_reporter_recover,
+		.dump = qed_fw_fatal_reporter_dump,
+};
+
+#define QED_REPORTER_FW_GRACEFUL_PERIOD 1200000
+
+void qed_fw_reporters_create(struct devlink *devlink)
+{
+	struct qed_devlink *dl = devlink_priv(devlink);
+
+	dl->fw_reporter = devlink_health_reporter_create(devlink, &qed_fw_fatal_reporter_ops,
+							 QED_REPORTER_FW_GRACEFUL_PERIOD, dl);
+	if (IS_ERR(dl->fw_reporter)) {
+		DP_NOTICE(dl->cdev, "Failed to create fw reporter, err = %ld\n",
+			  PTR_ERR(dl->fw_reporter));
+		dl->fw_reporter = NULL;
+	}
+}
+
+void qed_fw_reporters_destroy(struct devlink *devlink)
+{
+	struct qed_devlink *dl = devlink_priv(devlink);
+	struct devlink_health_reporter *rep;
+
+	rep = dl->fw_reporter;
+
+	if (!IS_ERR_OR_NULL(rep))
+		devlink_health_reporter_destroy(rep);
+}
+
+static int qed_dl_param_get(struct devlink *dl, u32 id,
+			    struct devlink_param_gset_ctx *ctx)
+{
+	struct qed_devlink *qed_dl = devlink_priv(dl);
+	struct qed_dev *cdev;
+
+	cdev = qed_dl->cdev;
+	ctx->val.vbool = cdev->iwarp_cmt;
+
+	return 0;
+}
+
+static int qed_dl_param_set(struct devlink *dl, u32 id,
+			    struct devlink_param_gset_ctx *ctx)
+{
+	struct qed_devlink *qed_dl = devlink_priv(dl);
+	struct qed_dev *cdev;
+
+	cdev = qed_dl->cdev;
+	cdev->iwarp_cmt = ctx->val.vbool;
+
+	return 0;
+}
+
+static const struct devlink_param qed_devlink_params[] = {
+	DEVLINK_PARAM_DRIVER(QED_DEVLINK_PARAM_ID_IWARP_CMT,
+			     "iwarp_cmt", DEVLINK_PARAM_TYPE_BOOL,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     qed_dl_param_get, qed_dl_param_set, NULL),
+};
+
+static int qed_devlink_info_get(struct devlink *devlink,
+				struct devlink_info_req *req,
+				struct netlink_ext_ack *extack)
+{
+	struct qed_devlink *qed_dl = devlink_priv(devlink);
+	struct qed_dev *cdev = qed_dl->cdev;
+	struct qed_dev_info *dev_info;
+	char buf[100];
+	int err;
+
+	dev_info = &cdev->common_dev_info;
+
+	err = devlink_info_driver_name_put(req, KBUILD_MODNAME);
+	if (err)
+		return err;
+
+	memcpy(buf, cdev->hwfns[0].hw_info.part_num, sizeof(cdev->hwfns[0].hw_info.part_num));
+	buf[sizeof(cdev->hwfns[0].hw_info.part_num)] = 0;
+
+	if (buf[0]) {
+		err = devlink_info_board_serial_number_put(req, buf);
+		if (err)
+			return err;
+	}
+
+	snprintf(buf, sizeof(buf), "%d.%d.%d.%d",
+		 GET_MFW_FIELD(dev_info->mfw_rev, QED_MFW_VERSION_3),
+		 GET_MFW_FIELD(dev_info->mfw_rev, QED_MFW_VERSION_2),
+		 GET_MFW_FIELD(dev_info->mfw_rev, QED_MFW_VERSION_1),
+		 GET_MFW_FIELD(dev_info->mfw_rev, QED_MFW_VERSION_0));
+
+	err = devlink_info_version_stored_put(req,
+					      DEVLINK_INFO_VERSION_GENERIC_FW_MGMT, buf);
+	if (err)
+		return err;
+
+	snprintf(buf, sizeof(buf), "%d.%d.%d.%d",
+		 dev_info->fw_major,
+		 dev_info->fw_minor,
+		 dev_info->fw_rev,
+		 dev_info->fw_eng);
+
+	return devlink_info_version_running_put(req,
+						DEVLINK_INFO_VERSION_GENERIC_FW_APP, buf);
+}
+
+static const struct devlink_ops qed_dl_ops = {
+	.info_get = qed_devlink_info_get,
+};
+
+struct devlink *qed_devlink_register(struct qed_dev *cdev)
+{
+	union devlink_param_value value;
+	struct qed_devlink *qdevlink;
+	struct devlink *dl;
+	int rc;
+
+	dl = devlink_alloc(&qed_dl_ops, sizeof(struct qed_devlink));
+	if (!dl)
+		return ERR_PTR(-ENOMEM);
+
+	qdevlink = devlink_priv(dl);
+	qdevlink->cdev = cdev;
+
+	rc = devlink_register(dl, &cdev->pdev->dev);
+	if (rc)
+		goto err_free;
+
+	rc = devlink_params_register(dl, qed_devlink_params,
+				     ARRAY_SIZE(qed_devlink_params));
+	if (rc)
+		goto err_unregister;
+
+	value.vbool = false;
+	devlink_param_driverinit_value_set(dl,
+					   QED_DEVLINK_PARAM_ID_IWARP_CMT,
+					   value);
+
+	devlink_params_publish(dl);
+	cdev->iwarp_cmt = false;
+
+	qed_fw_reporters_create(dl);
+
+	return dl;
+
+err_unregister:
+	devlink_unregister(dl);
+
+err_free:
+	devlink_free(dl);
+
+	return ERR_PTR(rc);
+}
+
+void qed_devlink_unregister(struct devlink *devlink)
+{
+	if (!devlink)
+		return;
+
+	qed_fw_reporters_destroy(devlink);
+
+	devlink_params_unregister(devlink, qed_devlink_params,
+				  ARRAY_SIZE(qed_devlink_params));
+
+	devlink_unregister(devlink);
+	devlink_free(devlink);
+}

drivers/net/ethernet/qlogic/qed/qed_devlink.h

+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Marvell/Qlogic FastLinQ NIC driver
+ *
+ * Copyright (C) 2020 Marvell International Ltd.
+ */
+#ifndef _QED_DEVLINK_H
+#define _QED_DEVLINK_H
+
+#include <linux/qed/qed_if.h>
+#include <net/devlink.h>
+
+struct devlink *qed_devlink_register(struct qed_dev *cdev);
+void qed_devlink_unregister(struct devlink *devlink);
+
+void qed_fw_reporters_create(struct devlink *devlink);
+void qed_fw_reporters_destroy(struct devlink *devlink);
+
+int qed_report_fatal_error(struct devlink *dl, enum qed_hw_err_type err_type);
+
+#endif

drivers/net/ethernet/qlogic/qed/qed_main.c

@@ -39,6 +39,7 @@
 #include "qed_hw.h"
 #include "qed_selftest.h"
 #include "qed_debug.h"
+#include "qed_devlink.h"
 
 #define QED_ROCE_QPS			(8192)
 #define QED_ROCE_DPIS			(8)
@@ -478,6 +479,7 @@ int qed_fill_dev_info(struct qed_dev *cdev,
 	}
 
 	dev_info->mtu = hw_info->mtu;
+	cdev->common_dev_info = *dev_info;
 
 	return 0;
 }
@@ -510,107 +512,6 @@ static int qed_set_power_state(struct qed_dev *cdev, pci_power_t state)
 	return 0;
 }
 
-struct qed_devlink {
-	struct qed_dev *cdev;
-};
-
-enum qed_devlink_param_id {
-	QED_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
-	QED_DEVLINK_PARAM_ID_IWARP_CMT,
-};
-
-static int qed_dl_param_get(struct devlink *dl, u32 id,
-			    struct devlink_param_gset_ctx *ctx)
-{
-	struct qed_devlink *qed_dl;
-	struct qed_dev *cdev;
-
-	qed_dl = devlink_priv(dl);
-	cdev = qed_dl->cdev;
-	ctx->val.vbool = cdev->iwarp_cmt;
-
-	return 0;
-}
-
-static int qed_dl_param_set(struct devlink *dl, u32 id,
-			    struct devlink_param_gset_ctx *ctx)
-{
-	struct qed_devlink *qed_dl;
-	struct qed_dev *cdev;
-
-	qed_dl = devlink_priv(dl);
-	cdev = qed_dl->cdev;
-	cdev->iwarp_cmt = ctx->val.vbool;
-
-	return 0;
-}
-
-static const struct devlink_param qed_devlink_params[] = {
-	DEVLINK_PARAM_DRIVER(QED_DEVLINK_PARAM_ID_IWARP_CMT,
-			     "iwarp_cmt", DEVLINK_PARAM_TYPE_BOOL,
-			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
-			     qed_dl_param_get, qed_dl_param_set, NULL),
-};
-
-static const struct devlink_ops qed_dl_ops;
-
-static int qed_devlink_register(struct qed_dev *cdev)
-{
-	union devlink_param_value value;
-	struct qed_devlink *qed_dl;
-	struct devlink *dl;
-	int rc;
-
-	dl = devlink_alloc(&qed_dl_ops, sizeof(*qed_dl));
-	if (!dl)
-		return -ENOMEM;
-
-	qed_dl = devlink_priv(dl);
-
-	cdev->dl = dl;
-	qed_dl->cdev = cdev;
-
-	rc = devlink_register(dl, &cdev->pdev->dev);
-	if (rc)
-		goto err_free;
-
-	rc = devlink_params_register(dl, qed_devlink_params,
-				     ARRAY_SIZE(qed_devlink_params));
-	if (rc)
-		goto err_unregister;
-
-	value.vbool = false;
-	devlink_param_driverinit_value_set(dl,
-					   QED_DEVLINK_PARAM_ID_IWARP_CMT,
-					   value);
-
-	devlink_params_publish(dl);
-	cdev->iwarp_cmt = false;
-
-	return 0;
-
-err_unregister:
-	devlink_unregister(dl);
-
-err_free:
-	cdev->dl = NULL;
-	devlink_free(dl);
-
-	return rc;
-}
-
-static void qed_devlink_unregister(struct qed_dev *cdev)
-{
-	if (!cdev->dl)
-		return;
-
-	devlink_params_unregister(cdev->dl, qed_devlink_params,
-				  ARRAY_SIZE(qed_devlink_params));
-
-	devlink_unregister(cdev->dl);
-	devlink_free(cdev->dl);
-}
-
 /* probing */
 static struct qed_dev *qed_probe(struct pci_dev *pdev,
 				 struct qed_probe_params *params)
@@ -639,12 +540,6 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev,
 	}
 	DP_INFO(cdev, "PCI init completed successfully\n");
 
-	rc = qed_devlink_register(cdev);
-	if (rc) {
-		DP_INFO(cdev, "Failed to register devlink.\n");
-		goto err2;
-	}
-
 	rc = qed_hw_prepare(cdev, QED_PCI_DEFAULT);
 	if (rc) {
 		DP_ERR(cdev, "hw prepare failed\n");
@@ -674,8 +569,6 @@ static void qed_remove(struct qed_dev *cdev)
 
 	qed_set_power_state(cdev, PCI_D3hot);
 
-	qed_devlink_unregister(cdev);
-
 	qed_free_cdev(cdev);
 }
 
@@ -2924,7 +2817,7 @@ static int qed_set_led(struct qed_dev *cdev, enum qed_led_mode mode)
 	return status;
 }
 
-static int qed_recovery_process(struct qed_dev *cdev)
+int qed_recovery_process(struct qed_dev *cdev)
 {
 	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
 	struct qed_ptt *p_ptt;
@@ -3112,6 +3005,9 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.get_link = &qed_get_current_link,
 	.drain = &qed_drain,
 	.update_msglvl = &qed_init_dp,
+	.devlink_register = qed_devlink_register,
+	.devlink_unregister = qed_devlink_unregister,
+	.report_fatal_error = qed_report_fatal_error,
 	.dbg_all_data = &qed_dbg_all_data,
 	.dbg_all_data_size = &qed_dbg_all_data_size,
 	.chain_alloc = &qed_chain_alloc,

drivers/net/ethernet/qlogic/qede/qede.h

@@ -172,6 +172,7 @@ struct qede_dev {
 	struct qed_dev			*cdev;
 	struct net_device		*ndev;
 	struct pci_dev			*pdev;
+	struct devlink			*devlink;
 
 	u32				dp_module;
 	u8				dp_level;
@@ -263,6 +264,7 @@ struct qede_dev {
 
 	struct bpf_prog			*xdp_prog;
 
+	enum qed_hw_err_type		last_err_type;
 	unsigned long			err_flags;
 #define QEDE_ERR_IS_HANDLED		31
 #define QEDE_ERR_ATTN_CLR_EN		0

drivers/net/ethernet/qlogic/qede/qede_main.c

@@ -1170,10 +1170,23 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 			rc = -ENOMEM;
 			goto err2;
 		}
+
+		edev->devlink = qed_ops->common->devlink_register(cdev);
+		if (IS_ERR(edev->devlink)) {
+			DP_NOTICE(edev, "Cannot register devlink\n");
+			edev->devlink = NULL;
+			/* Go on, we can live without devlink */
+		}
 	} else {
 		struct net_device *ndev = pci_get_drvdata(pdev);
 
 		edev = netdev_priv(ndev);
+
+		if (edev->devlink) {
+			struct qed_devlink *qdl = devlink_priv(edev->devlink);
+
+			qdl->cdev = cdev;
+		}
 		edev->cdev = cdev;
 		memset(&edev->stats, 0, sizeof(edev->stats));
 		memcpy(&edev->dev_info, &dev_info, sizeof(dev_info));
@@ -1225,7 +1238,10 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 err4:
 	qede_rdma_dev_remove(edev, (mode == QEDE_PROBE_RECOVERY));
 err3:
-	free_netdev(edev->ndev);
+	if (mode != QEDE_PROBE_RECOVERY)
+		free_netdev(edev->ndev);
+	else
+		edev->cdev = NULL;
 err2:
 	qed_ops->common->slowpath_stop(cdev);
 err1:
@@ -1296,6 +1312,11 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 	qed_ops->common->slowpath_stop(cdev);
 	if (system_state == SYSTEM_POWER_OFF)
 		return;
+
+	if (mode != QEDE_REMOVE_RECOVERY && edev->devlink) {
+		qed_ops->common->devlink_unregister(edev->devlink);
+		edev->devlink = NULL;
+	}
 	qed_ops->common->remove(cdev);
 	edev->cdev = NULL;
 
@@ -2455,7 +2476,8 @@ static int qede_close(struct net_device *ndev)
 
 	qede_unload(edev, QEDE_UNLOAD_NORMAL, false);
 
-	edev->ops->common->update_drv_state(edev->cdev, false);
+	if (edev->cdev)
+		edev->ops->common->update_drv_state(edev->cdev, false);
 
 	return 0;
 }
@@ -2577,19 +2599,12 @@ static void qede_atomic_hw_err_handler(struct qede_dev *edev)
 
 static void qede_generic_hw_err_handler(struct qede_dev *edev)
 {
-	struct qed_dev *cdev = edev->cdev;
-
 	DP_NOTICE(edev,
 		  "Generic sleepable HW error handling started - err_flags 0x%lx\n",
 		  edev->err_flags);
 
-	/* Trigger a recovery process.
-	 * This is placed in the sleep requiring section just to make
-	 * sure it is the last one, and that all the other operations
-	 * were completed.
-	 */
-	if (test_bit(QEDE_ERR_IS_RECOVERABLE, &edev->err_flags))
-		edev->ops->common->recovery_process(cdev);
+	if (edev->devlink)
+		edev->ops->common->report_fatal_error(edev->devlink, edev->last_err_type);
 
 	clear_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags);
 
@@ -2643,6 +2658,7 @@ static void qede_schedule_hw_err_handler(void *dev,
 		return;
 	}
 
+	edev->last_err_type = err_type;
 	qede_set_hw_err_flags(edev, err_type);
 	qede_atomic_hw_err_handler(edev);
 	set_bit(QEDE_SP_HW_ERR, &edev->sp_flags);

include/linux/qed/qed_if.h

@@ -21,6 +21,7 @@
 #include <linux/qed/common_hsi.h>
 #include <linux/qed/qed_chain.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
+#include <net/devlink.h>
 
 enum dcbx_protocol_type {
 	DCBX_PROTOCOL_ISCSI,
@@ -779,6 +780,11 @@ enum qed_nvm_flash_cmd {
 	QED_NVM_FLASH_CMD_NVM_MAX,
 };
 
+struct qed_devlink {
+	struct qed_dev *cdev;
+	struct devlink_health_reporter *fw_reporter;
+};
+
 struct qed_common_cb_ops {
 	void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc);
 	void (*link_update)(void *dev, struct qed_link_output *link);
@@ -844,10 +850,9 @@ struct qed_common_ops {
 	struct qed_dev*	(*probe)(struct pci_dev *dev,
 				 struct qed_probe_params *params);
 
-	void		(*remove)(struct qed_dev *cdev);
+	void (*remove)(struct qed_dev *cdev);
 
-	int		(*set_power_state)(struct qed_dev *cdev,
-					   pci_power_t state);
+	int (*set_power_state)(struct qed_dev *cdev, pci_power_t state);
 
 	void (*set_name) (struct qed_dev *cdev, char name[]);
 
@@ -855,50 +860,51 @@ struct qed_common_ops {
 	 * PF params required for the call before slowpath_start is
 	 * documented within the qed_pf_params structure definition.
 	 */
-	void		(*update_pf_params)(struct qed_dev *cdev,
-					    struct qed_pf_params *params);
-	int		(*slowpath_start)(struct qed_dev *cdev,
-					  struct qed_slowpath_params *params);
+	void (*update_pf_params)(struct qed_dev *cdev,
+				 struct qed_pf_params *params);
 
-	int		(*slowpath_stop)(struct qed_dev *cdev);
+	int (*slowpath_start)(struct qed_dev *cdev,
+			      struct qed_slowpath_params *params);
+
+	int (*slowpath_stop)(struct qed_dev *cdev);
 
 	/* Requests to use `cnt' interrupts for fastpath.
 	 * upon success, returns number of interrupts allocated for fastpath.
 	 */
-	int		(*set_fp_int)(struct qed_dev *cdev,
-				      u16 cnt);
+	int (*set_fp_int)(struct qed_dev *cdev, u16 cnt);
 
 	/* Fills `info' with pointers required for utilizing interrupts */
-	int		(*get_fp_int)(struct qed_dev *cdev,
-				      struct qed_int_info *info);
-
-	u32		(*sb_init)(struct qed_dev *cdev,
-				   struct qed_sb_info *sb_info,
-				   void *sb_virt_addr,
-				   dma_addr_t sb_phy_addr,
-				   u16 sb_id,
-				   enum qed_sb_type type);
-
-	u32		(*sb_release)(struct qed_dev *cdev,
-				      struct qed_sb_info *sb_info,
-				      u16 sb_id,
-				      enum qed_sb_type type);
-
-	void		(*simd_handler_config)(struct qed_dev *cdev,
-					       void *token,
-					       int index,
-					       void (*handler)(void *));
-
-	void		(*simd_handler_clean)(struct qed_dev *cdev,
-					      int index);
-	int (*dbg_grc)(struct qed_dev *cdev,
-		       void *buffer, u32 *num_dumped_bytes);
+	int (*get_fp_int)(struct qed_dev *cdev, struct qed_int_info *info);
+
+	u32 (*sb_init)(struct qed_dev *cdev,
+		       struct qed_sb_info *sb_info,
+		       void *sb_virt_addr,
+		       dma_addr_t sb_phy_addr,
+		       u16 sb_id,
+		       enum qed_sb_type type);
+
+	u32 (*sb_release)(struct qed_dev *cdev,
+			  struct qed_sb_info *sb_info,
+			  u16 sb_id,
+			  enum qed_sb_type type);
+
+	void (*simd_handler_config)(struct qed_dev *cdev,
+				    void *token,
+				    int index,
+				    void (*handler)(void *));
+
+	void (*simd_handler_clean)(struct qed_dev *cdev, int index);
+
+	int (*dbg_grc)(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes);
 
 	int (*dbg_grc_size)(struct qed_dev *cdev);
 
-	int (*dbg_all_data) (struct qed_dev *cdev, void *buffer);
+	int (*dbg_all_data)(struct qed_dev *cdev, void *buffer);
 
-	int (*dbg_all_data_size) (struct qed_dev *cdev);
+	int (*dbg_all_data_size)(struct qed_dev *cdev);
+
+	int (*report_fatal_error)(struct devlink *devlink,
+				  enum qed_hw_err_type err_type);
 
 /**
  * @brief can_link_change - can the instance change the link or not
@@ -1137,6 +1143,10 @@ struct qed_common_ops {
  *
  */
 	int (*set_grc_config)(struct qed_dev *cdev, u32 cfg_id, u32 val);
+
+	struct devlink* (*devlink_register)(struct qed_dev *cdev);
+
+	void (*devlink_unregister)(struct devlink *devlink);
 };
 
 #define MASK_FIELD(_name, _value) \